International Conference on Machine Learning 2019
TU the only university from Germany among the Top 50 contributing universities
2019/05/29 by Kersting/Peters
Machine learning experts from around the world will gather at the 36th International Conference on Machine Learning (ICML) to present the latest advances in machine learning understanding. The International Conference on Machine Learning is one of the most prestigious conferences for peer-reviewed research in Machine Learning, alongside NeurIPS, ICLR and others. And ICML is of the most relevant to Deep Learning (DL), although NeurIPS has a longer DL tradition and ICLR, being more focused, has a higher DL density.
Despite the strong industrial interest and massive contributions from companies like Google, Microsoft or Facebook, the 2019 International Conference on Machine Learning remains an academic conference. Summing up the relative contribution of academia and industry for all papers (i.e. number of industrial/academic affiliations divided by number of total affiliations per paper), 77 percent of the contribution are from academia such as the TU Darmstadt. Researchers from the TU Darmstadt have co-authored six papers at ICML 2019, and the research will be presented in oral paper and poster sessions.
The researchers from the TU Darmstadt are also organizing and participating in workshops throughout the conference. The low acceptance rate of 23 percent allows to keep highest quality of all accepted and peer-reviewed papers.
Leading in AI
Professor Kristian Kersting, head of the Machine Learning group and initiator of the AI-DA network at the TU Darmstadt, and Professor Jan Peters, PhD, are excited. These numbers show that the TU Darmstadt succeeds in its mission of being a leading AI university not only in Europe but also in the world. Actually, the TU Darmstadt is the only University from Germany among the Top 50 contributing academic institutions at ICML 2019.
Publications
Karl Stelzner, Robert Peharz, Kristian Kersting: Faster Attend-Infer-Repeat with Tractable Probabilistic Models, Proceedings of the 36th International Conference on Machine Learning, PMLR 97:5966-5975, 2019.
Philip Becker-Ehmck, Jan Peters, Patrick Van Der Smagt: Switching Linear Dynamics for Variational Bayes Filtering, Proceedings of the 36th International Conference on Machine Learning, PMLR 97:553-562, 2019.
Riad Akrour, Joni Pajarinen, Jan Peters, Gerhard Neumann: Projections for Approximate Policy Iteration Algorithms, Proceedings of the 36th International Conference on Machine Learning, PMLR 97:181-190, 2019.
Christian Wildner, Heinz Koeppl: Moment-Based Variational Inference for Markov Jump Processes, Proceedings of the 36th International Conference on Machine Learning, PMLR 97:6766-6775, 2019.
Jinseok Nam, Young-Bum Kim, Eneldo Loza Mencia, Sunghyun Park, Ruhi Sarikaya, Johannes Fürnkranz: Learning Context-dependent Label Permutations for Multi-label Classification, Proceedings of the 36th International Conference on Machine Learning, PMLR 97:4733-4742, 2019.
Philipp Becker, Harit Pandya, Gregor Gebhardt, Cheng Zhao, C. James Taylor, Gerhard Neumann: Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces, Proceedings of the 36th International Conference on Machine Learning, PMLR 97:544-552, 2019.
